dot-gpvam_estep: Conditional or prediction-error moments for an LMM E-step

.gpvam_estepR Documentation

Conditional or prediction-error moments for an LMM E-step

Description

Conditional or prediction-error moments for an LMM E-step

Usage

.gpvam_estep(X, Y, Z, R_inv, ybetas, G, REML = FALSE, profile = REML)

Arguments

X, Y, Z

Fixed-effects design, response, and random-effects design.

R_inv, G

Residual precision and random-effects covariance matrices.

ybetas

Current fixed-effects coefficients (ML).

REML

Use prediction-error moments and generalized least squares.

profile

Recompute generalized least squares even for ML.

Value

Random-effect covariance with mean, likelihood, and covariance blocks attached as attributes.


GPvam documentation built on Oct. 23, 2026, 1:06 a.m.